Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4608 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4255. Min Range: -7.4255
Max Act: 7.4255. Min Act: -0.1700
Data Index: 4316079 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.9880. Min Act: -0.1700
Data Index: 793961 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.7693. Min Act: -0.1700
Data Index: 6937896 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.7380. Min Act: -0.1700
Data Index: 5959707 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.6443. Min Act: -0.1700
Data Index: 6953399 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5505. Min Act: -0.1700
Data Index: 395873 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5505. Min Act: -0.1700
Data Index: 2038971 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5818. Min Act: -0.1700
Data Index: 6529143 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5818. Min Act: -0.1700
Data Index: 4006618 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5818. Min Act: -0.1700
Data Index: 1109717 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5818. Min Act: -0.1700
Data Index: 7034890 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5505. Min Act: -0.1700
Data Index: 6163452 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5193. Min Act: -0.1700
Data Index: 5385168 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5193. Min Act: -0.1700
Data Index: 5578414 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.4880. Min Act: -0.1700
Data Index: 3210298 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5193. Min Act: -0.1700
Data Index: 5821246 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5193. Min Act: -0.1700
Data Index: 5731375 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.4880. Min Act: -0.1700
Data Index: 8081868 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.4880. Min Act: -0.1700
Data Index: 8459830 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4255. Min Range: -7.4255
Max Act: 6.5193. Min Act: -0.1700
Data Index: 1248786 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19